{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:APMMUTZ6ROKWOV7DDK5BVBZZKH","short_pith_number":"pith:APMMUTZ6","canonical_record":{"source":{"id":"2307.08016","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-16T11:54:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6b99534296a7467545fdf40dc6904f8bd9214bf490a4f16f37460c4ae44a2dea","abstract_canon_sha256":"6eb86bda7fe34820ad7b241eca1d376993c0c70fd0795a8bcdad3df661be1754"},"schema_version":"1.0"},"canonical_sha256":"03d8ca4f3e8b956757e31aba1a873951d021cc71acc2430cbe297946e9e00251","source":{"kind":"arxiv","id":"2307.08016","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.08016","created_at":"2026-07-05T06:31:18Z"},{"alias_kind":"arxiv_version","alias_value":"2307.08016v1","created_at":"2026-07-05T06:31:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.08016","created_at":"2026-07-05T06:31:18Z"},{"alias_kind":"pith_short_12","alias_value":"APMMUTZ6ROKW","created_at":"2026-07-05T06:31:18Z"},{"alias_kind":"pith_short_16","alias_value":"APMMUTZ6ROKWOV7D","created_at":"2026-07-05T06:31:18Z"},{"alias_kind":"pith_short_8","alias_value":"APMMUTZ6","created_at":"2026-07-05T06:31:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:APMMUTZ6ROKWOV7DDK5BVBZZKH","target":"record","payload":{"canonical_record":{"source":{"id":"2307.08016","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-16T11:54:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6b99534296a7467545fdf40dc6904f8bd9214bf490a4f16f37460c4ae44a2dea","abstract_canon_sha256":"6eb86bda7fe34820ad7b241eca1d376993c0c70fd0795a8bcdad3df661be1754"},"schema_version":"1.0"},"canonical_sha256":"03d8ca4f3e8b956757e31aba1a873951d021cc71acc2430cbe297946e9e00251","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:31:18.890910Z","signature_b64":"qpplLeWdS/bd9lsFeRhy4c4QwCEQTeIvp4Gf+OiZpj1nUlXBe32yNweRXT7pjx4T3t/5D+OAcUAIDZj0iIfgBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"03d8ca4f3e8b956757e31aba1a873951d021cc71acc2430cbe297946e9e00251","last_reissued_at":"2026-07-05T06:31:18.890482Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:31:18.890482Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.08016","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:31:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i8oxeqKo9CvTiXi8cJ1xSx4/N9FIAtsxeZLdOk3sOq4C6HZs6AyyatOu8HYZThuamc4oPaiATpckwLWK5OYUAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T19:38:28.831881Z"},"content_sha256":"dc5bf8ba4faa3faa93c6a38507102d56e59b81a9bdbb237a447e98862d68032b","schema_version":"1.0","event_id":"sha256:dc5bf8ba4faa3faa93c6a38507102d56e59b81a9bdbb237a447e98862d68032b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:APMMUTZ6ROKWOV7DDK5BVBZZKH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Breaking Down the Task: A Unit-Grained Hybrid Training Framework for Vision and Language Decision Making","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jiwen Zhang, Ruipu Luo, Zhongyu Wei","submitted_at":"2023-07-16T11:54:16Z","abstract_excerpt":"Vision language decision making (VLDM) is a challenging multimodal task. The agent have to understand complex human instructions and complete compositional tasks involving environment navigation and object manipulation. However, the long action sequences involved in VLDM make the task difficult to learn. From an environment perspective, we find that task episodes can be divided into fine-grained \\textit{units}, each containing a navigation phase and an interaction phase. Since the environment within a unit stays unchanged, we propose a novel hybrid-training framework that enables active explor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.08016","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2307.08016/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:31:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xqdwQnRfOM39jQN8DVvAsd72sNsUTfoxSuSvWHhWn+dTZ/cVG3w//y9jruJB5ZXvV5u0pqHXQWm5LKdKF2yfBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T19:38:28.832829Z"},"content_sha256":"5de7249dca5364cbb8069db160bcb2b583a7dd7ecd9c4bb21bc7c76666426051","schema_version":"1.0","event_id":"sha256:5de7249dca5364cbb8069db160bcb2b583a7dd7ecd9c4bb21bc7c76666426051"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/APMMUTZ6ROKWOV7DDK5BVBZZKH/bundle.json","state_url":"https://pith.science/pith/APMMUTZ6ROKWOV7DDK5BVBZZKH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/APMMUTZ6ROKWOV7DDK5BVBZZKH/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-07T19:38:28Z","links":{"resolver":"https://pith.science/pith/APMMUTZ6ROKWOV7DDK5BVBZZKH","bundle":"https://pith.science/pith/APMMUTZ6ROKWOV7DDK5BVBZZKH/bundle.json","state":"https://pith.science/pith/APMMUTZ6ROKWOV7DDK5BVBZZKH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/APMMUTZ6ROKWOV7DDK5BVBZZKH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:APMMUTZ6ROKWOV7DDK5BVBZZKH","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"6eb86bda7fe34820ad7b241eca1d376993c0c70fd0795a8bcdad3df661be1754","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-16T11:54:16Z","title_canon_sha256":"6b99534296a7467545fdf40dc6904f8bd9214bf490a4f16f37460c4ae44a2dea"},"schema_version":"1.0","source":{"id":"2307.08016","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.08016","created_at":"2026-07-05T06:31:18Z"},{"alias_kind":"arxiv_version","alias_value":"2307.08016v1","created_at":"2026-07-05T06:31:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.08016","created_at":"2026-07-05T06:31:18Z"},{"alias_kind":"pith_short_12","alias_value":"APMMUTZ6ROKW","created_at":"2026-07-05T06:31:18Z"},{"alias_kind":"pith_short_16","alias_value":"APMMUTZ6ROKWOV7D","created_at":"2026-07-05T06:31:18Z"},{"alias_kind":"pith_short_8","alias_value":"APMMUTZ6","created_at":"2026-07-05T06:31:18Z"}],"graph_snapshots":[{"event_id":"sha256:5de7249dca5364cbb8069db160bcb2b583a7dd7ecd9c4bb21bc7c76666426051","target":"graph","created_at":"2026-07-05T06:31:18Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2307.08016/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision language decision making (VLDM) is a challenging multimodal task. The agent have to understand complex human instructions and complete compositional tasks involving environment navigation and object manipulation. However, the long action sequences involved in VLDM make the task difficult to learn. From an environment perspective, we find that task episodes can be divided into fine-grained \\textit{units}, each containing a navigation phase and an interaction phase. Since the environment within a unit stays unchanged, we propose a novel hybrid-training framework that enables active explor","authors_text":"Jiwen Zhang, Ruipu Luo, Zhongyu Wei","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-16T11:54:16Z","title":"Breaking Down the Task: A Unit-Grained Hybrid Training Framework for Vision and Language Decision Making"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.08016","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:dc5bf8ba4faa3faa93c6a38507102d56e59b81a9bdbb237a447e98862d68032b","target":"record","created_at":"2026-07-05T06:31:18Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"6eb86bda7fe34820ad7b241eca1d376993c0c70fd0795a8bcdad3df661be1754","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-16T11:54:16Z","title_canon_sha256":"6b99534296a7467545fdf40dc6904f8bd9214bf490a4f16f37460c4ae44a2dea"},"schema_version":"1.0","source":{"id":"2307.08016","kind":"arxiv","version":1}},"canonical_sha256":"03d8ca4f3e8b956757e31aba1a873951d021cc71acc2430cbe297946e9e00251","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"03d8ca4f3e8b956757e31aba1a873951d021cc71acc2430cbe297946e9e00251","first_computed_at":"2026-07-05T06:31:18.890482Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:31:18.890482Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qpplLeWdS/bd9lsFeRhy4c4QwCEQTeIvp4Gf+OiZpj1nUlXBe32yNweRXT7pjx4T3t/5D+OAcUAIDZj0iIfgBw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:31:18.890910Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.08016","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dc5bf8ba4faa3faa93c6a38507102d56e59b81a9bdbb237a447e98862d68032b","sha256:5de7249dca5364cbb8069db160bcb2b583a7dd7ecd9c4bb21bc7c76666426051"],"state_sha256":"711e2b444f93b06a3d60b77b1356def9c5c26cfcc1a26725c7d223e61ceb6420"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7pO+gGEMeLmutyVPljpVDeh8ILtNRkn4rpm34/oE5xNOVFa3i4s55rHLMUa4qi/T+JP4M5lGV+JnMdy/oZr0Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T19:38:28.875444Z","bundle_sha256":"8870ca35e4bbe705a4e108788748bd1f5f53b06c6d517c5f2d7869afca8e8265"}}